arXiv (All)
open access
SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understanding but inherit toxic signals from weakly curated pretraining corpora, leading to explicitly toxic outputs, especially under adversarial triggers that late, o
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification#797286
- Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge Conflict#819989
- Human-Centric Image Captioning with Subject-Centered Spatial Understanding#985668
- From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling#819535
- From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling#809539
Record · ID 798700
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive